Thread

Strands Harness

150 points · 97 comments · zuckerborg0101

fxwin · 1790177062 · focus · HN ↗
why would you include oh-my-pi in the comparison but not vanilla pi?
1. chaos_emergent · 1790177501 · focus · HN ↗
  Am I wrong in saying that the interfaces presented to the model in OMP versus plain old Pi are identical?
  1. c0rruptbytes · 1790177815 · focus · HN ↗
    OMP has a lot of candy that raises token cost compared to vanilla pi
  2. fxwin · 1790188811 · focus · HN ↗
    it's less about the interfaces and more that it feels disingenuous to compare token usage to a pi setup that injects a bunch of stuff into context rather than the base version. it makes me think they tested it with pi, found they couldnt meaningfully beat its token usage + pass rate, and omitted the comparison. i'd love to be proven wrong, but this seems like the easy explanation
2. jbellis · 1790181183 · focus · HN ↗
  Because vanilla pi doesn't do a lot of important things out of the box, and they didn't want to open the "which extensions should we add" can of worms.
  1. fxwin · 1790188882 · focus · HN ↗
    if anything, using oh-my-pi opened that can more than using pi (or better: both!) would have

Unofficial Hacker News client; not affiliated with Y Combinator.